Research and Development Expenditures and Economic Growth: A Panel Data Analysis

Rita Freimane


Theoretically, for achieving long term economic growth the amount of investments in research and development (R&D) is highly important. R&D plays major role in innovation, raising productivity and increasing economic growth. Therefore, R&D expenditures should have a positive and persistent effect on growth. However, empirically the direct effect can be measured with difficulty because of the lag. There are different empirical findings about relationship between research and development and economic growth based on econometrical modelling. Our study differs from previous analyses with emphasis on details: how sensitive are the results to panel data model’s specification, what are differences between developed and developing countries in the EU.

The main purpose of the paper is to re-examine the empirical relationship between research and development (R&D) expenditures and economic growth in European Union member states. The paper tries to answer the question whether the impact of R&D investments on growth differs between old and new EU members.

Empirical analysis is based on panel data model estimation. The sample was made from a state-level panel data (EU countries) for time period 2001-2013. For the robustness of results four categories of panel model specification are compared: (1) fixed effects model, (2) random effects model, (3) heterogeneous parameter model and (4) linear dynamic model. An overview of the substantive consideration relevant to different statistical specifications is provided.

The results are sensitive to the model specification and to the sub-sample analysed. We run separate regressions for old (EU-15) and new (EU-13) member states, since these subsamples differ substantially in terms of their level of socio-economic development, tax systems and institutional quality. The following explanatory variables are chosen: investment rate, lagged level of GDP per capita, openness and research and development expenditures. Initial analysis (fixed effect models) showed that coefficients of R&D were significant and positive only in EU-15. Thus, returns on increases in R&D expenditures seemed to be questionable, particularly in the new member states. However, the later analysis showed that results depend on the panel data model specification issues.

The analysis is proceeded with an examination of the causal relationship between R&D expenditures and economic growth. Causality tests highlighted differences between old and new EU member states even more.

The results indicate that the relationship between research and development expenditures and economic growth are more complex and ambiguous than expected. The analysis can be proceeded with distinguishing between effects of private and public R&D investments.


The theoretical contribution. Several potential problems of different panel models are demonstrated.

Practical implications (if applicable). The paper can be used for discussions on how to choose among different panel model specifications.

Keywords: research and development expenditures, economic growth, panel data model.

Paper type: Research paper.



  • There are currently no refbacks.

KTU_school_economics and business Riga Technical University
Brno University of Technology Tallinn University of Technology